{"id":"https://openalex.org/W4417470505","doi":"https://doi.org/10.1109/tgrs.2025.3645820","title":"CMAI-Det: Cross-Modal Alignment and Interaction for RGB-T Object Detection in Drone Scenes","display_name":"CMAI-Det: Cross-Modal Alignment and Interaction for RGB-T Object Detection in Drone Scenes","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4417470505","doi":"https://doi.org/10.1109/tgrs.2025.3645820"},"language":null,"primary_location":{"id":"doi:10.1109/tgrs.2025.3645820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3645820","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089535238","display_name":"Xin Wen","orcid":"https://orcid.org/0000-0002-8722-5602"},"institutions":[{"id":"https://openalex.org/I157507598","display_name":"Shenyang University of Technology","ror":"https://ror.org/00d7f8730","country_code":"CN","type":"education","lineage":["https://openalex.org/I157507598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wen","raw_affiliation_strings":["School of Software Engineering, Shenyang University of Technology, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-8722-5602","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Shenyang University of Technology, Shenyang, China","institution_ids":["https://openalex.org/I157507598"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109378419","display_name":"Heng Yin","orcid":"https://orcid.org/0009-0000-8188-5901"},"institutions":[{"id":"https://openalex.org/I157507598","display_name":"Shenyang University of Technology","ror":"https://ror.org/00d7f8730","country_code":"CN","type":"education","lineage":["https://openalex.org/I157507598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haixu Yin","raw_affiliation_strings":["School of Software Engineering, Shenyang University of Technology, Shenyang, China"],"raw_orcid":"https://orcid.org/0009-0000-8188-5901","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Shenyang University of Technology, Shenyang, China","institution_ids":["https://openalex.org/I157507598"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kai Li","orcid":"https://orcid.org/0009-0001-9968-1787"},"institutions":[{"id":"https://openalex.org/I157507598","display_name":"Shenyang University of Technology","ror":"https://ror.org/00d7f8730","country_code":"CN","type":"education","lineage":["https://openalex.org/I157507598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Li","raw_affiliation_strings":["School of Software Engineering, Shenyang University of Technology, Shenyang, China"],"raw_orcid":"https://orcid.org/0009-0001-9968-1787","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Shenyang University of Technology, Shenyang, China","institution_ids":["https://openalex.org/I157507598"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wanying Nie","orcid":"https://orcid.org/0009-0009-3817-0690"},"institutions":[{"id":"https://openalex.org/I157507598","display_name":"Shenyang University of Technology","ror":"https://ror.org/00d7f8730","country_code":"CN","type":"education","lineage":["https://openalex.org/I157507598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanying Nie","raw_affiliation_strings":["School of Software Engineering, Shenyang University of Technology, Shenyang, China"],"raw_orcid":"https://orcid.org/0009-0009-3817-0690","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Shenyang University of Technology, Shenyang, China","institution_ids":["https://openalex.org/I157507598"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100308192","display_name":"Jianxun Zhao","orcid":"https://orcid.org/0009-0005-5541-5996"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxun Zhao","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0009-0005-5541-5996","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010927997","display_name":"Kechen Song","orcid":"https://orcid.org/0000-0002-7636-3460"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kechen Song","raw_affiliation_strings":["School of Mechanical Engineering and Automation, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-7636-3460","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5932,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.95435649,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.853600025177002,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.853600025177002,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11133","display_name":"UAV Applications and Optimization","score":0.05079999938607216,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.01510000042617321,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8370000123977661},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7615000009536743},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.7376999855041504},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47029998898506165},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4659999907016754},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.40779998898506165},{"id":"https://openalex.org/keywords/image-sensor","display_name":"Image sensor","score":0.3425999879837036},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.33629998564720154}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8370000123977661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8126999735832214},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7615000009536743},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.7376999855041504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7049000263214111},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6679999828338623},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C76935873","wikidata":"https://www.wikidata.org/wiki/Q209121","display_name":"Image sensor","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.25780001282691956},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2025.3645820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3645820","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5220864097","display_name":null,"funder_award_id":"2023-MSLH-246","funder_id":"https://openalex.org/F4320323086","funder_display_name":"Natural Science Foundation of Liaoning Province"},{"id":"https://openalex.org/G5881418445","display_name":null,"funder_award_id":"62306186","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323086","display_name":"Natural Science Foundation of Liaoning Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2883279456","https://openalex.org/W2987131085","https://openalex.org/W3155938136","https://openalex.org/W3186570689","https://openalex.org/W3207919963","https://openalex.org/W4312596062","https://openalex.org/W4313007055","https://openalex.org/W4313893207","https://openalex.org/W4323666945","https://openalex.org/W4367721788","https://openalex.org/W4385801610","https://openalex.org/W4386066010","https://openalex.org/W4386071535","https://openalex.org/W4386189887","https://openalex.org/W4386591405","https://openalex.org/W4386813311","https://openalex.org/W4387968493","https://openalex.org/W4389665201","https://openalex.org/W4390659919","https://openalex.org/W4390787329","https://openalex.org/W4390874259","https://openalex.org/W4391102597","https://openalex.org/W4391376377","https://openalex.org/W4392796741","https://openalex.org/W4393042122","https://openalex.org/W4396523238","https://openalex.org/W4396754494","https://openalex.org/W4401806723","https://openalex.org/W4402569181","https://openalex.org/W4402704573","https://openalex.org/W4402753999","https://openalex.org/W4402754006","https://openalex.org/W4402775842","https://openalex.org/W4403022803","https://openalex.org/W4403022807","https://openalex.org/W4403977303","https://openalex.org/W4404909569","https://openalex.org/W4405179719","https://openalex.org/W4406858089","https://openalex.org/W4407247101","https://openalex.org/W4407375775","https://openalex.org/W4408245958","https://openalex.org/W4412404174","https://openalex.org/W4415209610"],"related_works":[],"abstract_inverted_index":{"RGB-T":[0,64,157],"object":[1,60,143],"detection":[2,47,61,127,190],"is":[3,106,194],"increasingly":[4],"applied":[5],"in":[6,18,62,159,188],"drone":[7,38,161],"surveillance,":[8],"autonomous":[9],"driving,":[10],"and":[11,29,42,79,96,135,179,186],"intelligent":[12],"transportation":[13],"due":[14],"to":[15,72,98,109,114],"its":[16,184],"robustness":[17,185],"complex":[19,189],"conditions.":[20],"However,":[21],"most":[22],"existing":[23],"methods":[24],"assume":[25],"well-aligned":[26],"image":[27],"pairs":[28],"often":[30],"overlook":[31],"misalignment":[32],"between":[33],"modalities,":[34],"which":[35],"arises":[36],"from":[37],"motion,":[39],"viewpoint":[40],"shifts,":[41],"sensor":[43],"inconsistencies,":[44],"thereby":[45],"hindering":[46],"accuracy.":[48],"To":[49],"address":[50],"this":[51],"limitation,":[52],"we":[53],"present":[54],"CMAI-Det,":[55],"a":[56,69,124],"framework":[57],"designed":[58],"for":[59],"unaligned":[63],"images.":[65],"The":[66,192],"approach":[67],"employs":[68],"dual-stream":[70],"extractor":[71],"strengthen":[73],"the":[74,87,148],"representational":[75],"capacity":[76],"of":[77,141,166,177,181],"visible":[78,100],"thermal":[80,88],"features.":[81,101],"A":[82],"modality-cooperative":[83],"alignment":[84],"module,":[85],"using":[86],"stream":[89],"as":[90],"reference,":[91],"integrates":[92],"multi-scale":[93],"deformable":[94,126],"convolutions":[95],"attention":[97],"align":[99],"An":[102],"adaptive":[103],"fusion":[104],"scheme":[105],"further":[107],"introduced":[108],"balance":[110],"modality":[111],"contributions":[112],"according":[113],"their":[115],"reliability":[116],"under":[117],"varying":[118],"conditions,":[119],"enhancing":[120],"feature":[121],"robustness.":[122],"Finally,":[123],"perception-driven":[125],"head":[128],"improves":[129],"discriminability":[130],"by":[131],"reinforcing":[132],"spatial":[133],"selectivity":[134],"structural":[136],"adaptability,":[137],"enabling":[138],"precise":[139],"modeling":[140],"diverse":[142],"appearances.":[144],"Extensive":[145],"experiments":[146],"on":[147],"DVTOD":[149],"dataset":[150],"show":[151],"that":[152],"CMAI-Det":[153],"surpasses":[154],"12":[155],"state-of-the-art":[156],"detectors":[158],"challenging":[160],"scenarios,":[162],"achieving":[163],"an":[164],"mAP":[165],"86.1.":[167],"It":[168],"also":[169],"performs":[170],"strongly":[171],"at":[172,196],"standard":[173],"thresholds,":[174],"with":[175],"AP50":[176],"90.0":[178],"AP75":[180],"82.3,":[182],"underscoring":[183],"effectiveness":[187],"tasks.":[191],"code":[193],"available":[195],"https://github.com/yinhaixu2000-coder/CMAI-Detection.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-31T23:11:33.660297","created_date":"2025-12-18T00:00:00"}